Parse raw sentences for custom tags, fix: #1903

hankcs · Aug 18, 2024 · 022d0fb · 022d0fb
1 parent b32d4b9
commit 022d0fb
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/hanlp/components/taggers/tagger.py b/hanlp/components/taggers/tagger.py
@@ -179,7 +179,9 @@ def build_samples(self, data: List[str], **kwargs):
     def prediction_to_human(self, pred_ids, vocab: List[str], batch):
         if isinstance(pred_ids, torch.Tensor):
             pred_ids = pred_ids.tolist()
-        sents = batch[self.config.token_key]
+        sents = batch.get(f'{self.config.token_key}_')
+        if not sents:
+            sents = batch[self.config.token_key]
         dict_tags: DictInterface = self.dict_tags
         for each, sent in zip(pred_ids, sents):
             tags = [vocab[id] for id in each[:len(sent)]]

diff --git a/hanlp/version.py b/hanlp/version.py
@@ -2,7 +2,7 @@
 # Author: hankcs
 # Date: 2019-12-28 19:26
 
-__version__ = '2.1.0-beta.58'
+__version__ = '2.1.0-beta.59'
 """HanLP version"""